Disease prediction and drug recommendation system using machine learning

Project Code :TCMAPY2299

Objective

This project develops a disease prediction and static drug recommendation system using machine learning. It allows users to input symptoms, which the system analyzes to predict diseases such as Diarrhoea, Asthma, Covid, Parkinson’s, and Malaria. Three machine learning algorithms—Decision Tree, Random Forest, and XGBoost—are employed for accurate classification. Following disease prediction, the system provides predefined drug information associated with the identified condition. The application includes essential modules for user registration, login, classification, and logout, ensuring controlled access. To protect sensitive user data, RSA encryption is implemented, securing information during storage. The backend is built with Python and the Flask framework, while the frontend uses HTML, CSS, and JavaScript for a user-friendly interface. Machine learning models are trained and validated using datasets sourced from Kaggle. By integrating symptom-based disease prediction, static drug recommendations, and data security features, the system offers a reliable and structured platform for healthcare support. This combination aims to facilitate timely, accurate disease identification while ensuring user privacy and data protection.

Abstract

This project presents a disease prediction and static drug recommendation system based on machine learning techniques. The system predicts diseases by analyzing symptoms provided by users. Diseases such as Diarrhoea, Asthma, Covid, Parkinson, and Malaria are classified using Decision Tree, Random Forest, and XG Boost algorithms. After prediction, the system displays predefined drug information related to the identified disease. The application includes user registration, login, classification, and logout modules to manage access. User data security is ensured through RSA encryption, which protects sensitive information during storage and processing. The backend is developed using Python with the Flask framework, while the frontend is designed using HTML, CSS, and JavaScript. Machine learning models are trained and tested using datasets collected from Kaggle. This project combines symptom-based classification, static recommendation display, and data security mechanisms into a single platform. The system aims to provide accurate disease prediction and reliable drug information in a structured and secure manner.

Keywords: Disease Prediction, Machine Learning, Decision Tree, Random Forest, XG Boost, Symptom Analysis, Static Drug Recommendation, Flask, RSA Encryption, Classification System

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.